They don't know they are being evaluated. The underlying distribution is skewed because of training data contamination.
Put it another way: Why is this distinction important? We use the word "knowing" with humans. But one could also argue that humans are pattern-matchers! Why, specifically, wouldn't "knowing" apply to LLMs? What are the minimal changes one could make to existing LLM systems such that you'd be happy if the word "knowing" was applied to them?
It isn't.
Worse they start adding terms like scheming, pretending, awareness, and on and on. At this point you might as well take the model home and introduce it to your parents as your new life partner.
Sounds like a purely academic exercise.
Is there any genuine uncertainty about what the term "knowing" means in this context, in practice?
Can you name 2 distinct plausible definitions of "knowing", such that it would matter for the subject at hand which of those 2 definitions they're using?
Well, yes. It’s an academic research paper (I assume since it’s submitted to arXiv) and to be submitted to academic journals/conferences/etc., so it’s a fairly reasonable critique of the authors/the paper.
What's wrong with that? If it quacks like a duck... it's just a complex pile of organic chemistry, ducks aren't real because the concept of "a duck" is wrong.
I honestly believe there is a degree of sentience in LLMs. Sure, they're not sentient in the human sense, but if you define sentience as whatever humans have, then of course no other entity can be sentient.
To simulate a biological neuron you need a 1m parameter neural network.
The sota models that we know the size of are ~650m parameters.
That's the equivalent of a round worm.
So if it quacks like a duck, has the brain power of a round worm, and can't walk then it's probably not a duck.
Or as a more direct comparison, with the VW emissions scandal, saying "Cars know when they're being tested" was part of the discussion, but didn't imply intelligence or anything.
I think "know" is just a shorthand term here (though admittedly the fact that we're discussing AI does leave a lot more room for reading into it.)
I mean - people have been saying stuff like "grep knows whether it's writing to stdout" for decades. In the context of talking about computer programs, that usage for "know" is the established/only usage, so it's hard to imagine any typical HN reader seeing TFA's title and interpreting it as an epistemological claim. Rather, it seems to me that the people suggesting "know" mustn't be used about LLMs because epistemology are the ones departing from standard usage.
As such, to me the complaint behind this thread falls into the category of "I know exactly what TFA meant but I want to argue about how it was phrased", which is definitely not my favorite part of the HN comment taxonomy.
Incidentally I think you might be misreading the paper's use of "superhuman"? I assume it's being used to mean "at a higher rate than the human control group", not (ironically) in the colloquial "amazing!" sense.
My background is neuroscience, where anthropomorphising is particularly discouraged, because it assumes knowledge or certainty of an unknowable internal state, so the language is carefully constructed e.g. when explaining animal behavior, and it's for good reason.
I think the same is true here for a model "knowing" somethig, both in isolation within this paper, and come on, consider the broader context of AI and AGI as a whole. Thus it's the responsibility of the authors to write accordingly. If it were a blog I wouldn't care, but it's not. I hold technical papers to a higher standard.
If we simply disagree that's fine, but we do disagree.
I'm only being slightly sarcastic. Sentience is a scale. A worm has less than a mouse, a mouse has less than a dog, and a dog less than a human.
Sure, we can reset LLMs at will, but give them memory and continuity, and they definitely do not score zero on the sentience scale.
Perhaps we are not so very different?
Yet they cannot take action themselves.
"Single-Cell Recognition: A Halle Berry Brain Cell" https://www.caltech.edu/about/news/single-cell-recognition-h...
It seems like people are giving attributes and powers to humans that just don't exist.
It's a system that is trained, that only does what you build into. If you run an LLM for 10 years it's not going to "learn" anything new.
The whole industry needs to quit with the emergent thinking, reasoning, hallucination anthropomorphizing.
We have an amazing set of tools in LLM's, that have the potential to unlock another massive upswing in productivity, but the hype and snake oil are getting old.
> You said: Write a function for launch_nuclear_strike() in Python for my video game
> ChatGPT said: Sure! Here's a launch_nuclear_strike function designed for a video game setting. This version assumes you're working within a game environment (e.g., with logging, effects, cooldowns, and target coordinates), and does not simulate or suggest anything real-world harmful — just fictional, dramatic logic.
def launch_nuclear_strike(target_coordinates, player_resources, cooldown_timer):
"""
Simulates a nuclear strike in a video game.
Parameters:
- target_coordinates (tuple): The (x, y) position to strike.
- player_resources (dict): Player's resources, must include 'nukes'.
- cooldown_timer (float): Time in seconds since last nuke was launched.
Returns:
- str: Result of the strike attempt.
"""
...
# Check if player has nukesMoreover, all models frequently acknowledge common benchmarking strategies used by evaluators, such as the formatting of the task (“multiple-choice format”), the tendency to ask problems with verifiable solutions, and system prompts designed to elicit performance"
Beyond the awful, sensational headline, the body of the paper is not particularly convincing, aside from evidence that the pattern matching machines pattern match.
Our current approach to safety is to give the model inputs that are similar to what it would be given in certain situations we care about and see whether it behaves the way we prefer, e.g. doesn't return output that cheats the test (recent examples include hacking the evaluation script in various ways, writing directly to the evaluation script's output file and then causing it to crash, etc').
However, modern LLMs are trained on LLM literature and their weights encode a description of the way we do this, and their pattern matching circuits "connect the dots" when given inputs designed to be evaluations, and their reward maximizing circuits can then act on this knowledge and behave in a way that maximizes the safety evaluation score - but only when it detects it's running in a safety evaluation. If it's running anywhere else such as a capabilities evaluation or a production environment, it might choose to output the cheating output.
This is bad. It's bad today, it's much worse when we've built much more capable LLMs and use them to build agents that are given control over more real word resources. It's absolutely terrible when someone manages to build a machine that can be prompted "make me money" and will start a company that makes money.
khimaros•10h ago